VART-X  0.3.0
vart_metaconvert_impl_base.hpp
Go to the documentation of this file.
1 /*
2  * Copyright 2024-2026 Advanced Micro Devices Inc.
3  *
4  * Licensed under the Apache License, Version 2.0 (the "License");
5  * you may not use this file except in compliance with the License.
6  * You may obtain a copy of the License at
7  *
8  * http://www.apache.org/licenses/LICENSE-2.0
9  *
10  * Unless required by applicable law or agreed to in writing, software
11  * distributed under the License is distributed on an "AS IS" BASIS,
12  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13  * See the License for the specific language governing permissions and
14  * limitations under the License.
15  */
16 
17 #pragma once
18 
24 #include "../vart_inferresult.hpp"
27 
30 namespace vart {
31 
39  public:
41  MetaConvertImplBase() = default;
42 
44  virtual ~MetaConvertImplBase() {}
45 
61  virtual std::shared_ptr<OverlayShapeInfo> prepare_overlay_meta(std::shared_ptr<InferResult> root_infer_res) = 0;
62 };
63 
64 } // namespace vart
Abstract interface for metaconvert implementation used by MetaConvert.
Definition: vart_metaconvert_impl_base.hpp:38
virtual std::shared_ptr< OverlayShapeInfo > prepare_overlay_meta(std::shared_ptr< InferResult > root_infer_res)=0
prepare_overlay_meta() - Converts inference results to data structures needed for overlay Overlay
virtual ~MetaConvertImplBase()
Virtual destructor to ensure proper cleanup of derived implementations.
Definition: vart_metaconvert_impl_base.hpp:44
MetaConvertImplBase()=default
Default construction is allowed for derived implementations.
VART (Vitis AI Runtime) public API namespace.
Abstract base class for InferResult implementation (pimpl).
Abstract base for platform-specific Overlay implementation (pimpl).